Learn about Data Types in Data Science for beginners
If you have newly started your data science and/or machine learning journey, you have probably come out to the word “data type”.
If you had expressions like the below picture, then you have come to the right place to clear all your confusion!
If you enjoy the article, do not forget to clap and follow for more content about deep learning and data science.
Let’s go!
The graphic below highlights the main classification of data types in data science.
Numerical means that data is represented with qualitive values (numbers). This type is divided into two groups: discrete and continues.
Discrete data is represented with integers, for example, 1, 2, 3, 9, 21, 55 and so on. It cannot have fraction part. Examples for discrete numerical data can be how many children a person has. A person cannot have 2.4 children, right?
On the other hand, continuous data has a fraction part. A quick example can be height of a man: 170.8 cm or amount in the bank account: 721.86 euros.
Coming to the categorical values, these are represented with classes. Classes can be named with words or numbers. Categorical data types are also divided into two groups according to the relationship between the classes: ordinal and nominal.
Classes in nominal data do not have superiority over each other. For example, in the case of t-shirt colors, it cannot be stated that blue is better than green or the other way around. A person can have his or her own opinion about colors, but it is not as concrete as “good” is higher than “bad” while voting for a service.
As you might have guessed, in ordinal data classes are ordered from “bad” to “good”. Let’s get into examples:
If you liked the article, you can clap and follow for support, and subscribe to get the new articles directly to you inbox whenever I publish.